Racism detection by analyzing differential opinions through sentiment analysis using stacked ensemble GCR-NN

Nithvika Reddy *, N. S. Manogna and Shaga Shivani

Department of Computer Science, Sreenidhi Institute of Science and Technology, India.
 
Review
International Journal of Science and Research Archive, 2023, 09(01), 231-235.
Article DOI: 10.30574/ijsra.2023.9.1.0389
Publication history: 
Received on 08 April 2023; revised on 20 May 2023; accepted on 23 May 2023
 
Abstract: 
Because of the unquestionable person of the stage on the worldwide field, a few surviving and new types of bias have arisen. Prejudice has surfaced through online entertainment in both concealed and open forms, concealed through the use of images and open through the distribution of discriminatory expressions under fake characters, to generate contempt, viciousness, and cultural flimsiness. Prejudice is currently flourishing on the basis of diversity, origin, language, culture, and, most importantly, religion, despite the fact that it is frequently associated with nationality. It has been deemed a grave threat to global harmony as well as social, political, and social fortitude that web-based entertainment's capacity to incite racial tensions. Therefore, it is necessary to keep an eye on social media, which serves as the primary channel through which racist ideas are disseminated, identify racist expressions, and swiftly criminalize them. By analyzing the sentiment of tweets, this study aims to identify biased tweets. By combining gated recurrent units (GRU), convolutional neural networks (CNN), and recurrent neural networks (RNN), gated convolutional recurrent neural networks (GCR-NN) are formed. This is done to make use of the superior presentation provided by deep learning. GRU is at the top of the GCR-NN model for extracting acceptable and recognizable characteristics from unrefined text, whereas CNN dissects fundamental components for RNN to create precision expectations. The proposed GCR-NN's presentation within the framework of machine learning (ML) and deep learning models is the subject of numerous analyses. The results show that GCR-NN performs better and has a precision of 0.98 that is higher. In 97% of tweets, the proposed GCR-NN model can recognize extremist remarks.
 
Keywords: 
Racism Detection; Sentiment Analysis; Stacked Ensemble GCR-NN; Analysis of Twitter; Racism Detection 
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0